summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorPavel Tatashin <pasha.tatashin@oracle.com>2017-07-06 15:39:14 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-07-06 16:24:33 -0700
commit9017217b6f45e9045b2621b02cbc5605a566b803 (patch)
tree7b3c5a784df699bce9ada4f741605c1098c5d868 /mm/page_alloc.c
parent3d375d78593cd5daeead34ed3279c4ff63dd04f2 (diff)
downloadlinux-9017217b6f45e9045b2621b02cbc5605a566b803.tar.gz
linux-9017217b6f45e9045b2621b02cbc5605a566b803.tar.bz2
linux-9017217b6f45e9045b2621b02cbc5605a566b803.zip
mm: adaptive hash table scaling
Allow hash tables to scale with memory but at slower pace, when HASH_ADAPT is provided every time memory quadruples the sizes of hash tables will only double instead of quadrupling as well. This algorithm starts working only when memory size reaches a certain point, currently set to 64G. This is example of dentry hash table size, before and after four various memory configurations: MEMORY SCALE HASH_SIZE old new old new 8G 13 13 8M 8M 16G 13 13 16M 16M 32G 13 13 32M 32M 64G 13 13 64M 64M 128G 13 14 128M 64M 256G 13 14 256M 128M 512G 13 15 512M 128M 1024G 13 15 1024M 256M 2048G 13 16 2048M 256M 4096G 13 16 4096M 512M 8192G 13 17 8192M 512M 16384G 13 17 16384M 1024M 32768G 13 18 32768M 1024M 65536G 13 18 65536M 2048M The effect of this change on runtime is undetectable as filesystem growth is not proportional to machine memory size as is currently assumed. The change effects only large memory machine. Additional tuning might be needed, but that can be done by the clients of the kmem_cache_create interface, not the generic cache allocator itself. The adaptive hashing is disabled on 32 bit systems to avoid confusion of whether base should be different for smaller systems, and to avoid overflows. [mhocko@suse.com: drop HASH_ADAPT] Link: http://lkml.kernel.org/r/20170509094607.GG6481@dhcp22.suse.cz [pasha.tatashin@oracle.com: UL -> ULL fix] Link: http://lkml.kernel.org/r/1495300013-653283-2-git-send-email-pasha.tatashin@oracle.com [pasha.tatashin@oracle.com: disable adaptive hash on 32 bit systems] Link: http://lkml.kernel.org/r/1495469329-755807-2-git-send-email-pasha.tatashin@oracle.com Link: http://lkml.kernel.org/r/1488432825-92126-5-git-send-email-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com> Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: David Miller <davem@davemloft.net> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Babu Moger <babu.moger@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c25
1 files changed, 25 insertions, 0 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 34240e2a0583..e0f138a47548 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7180,6 +7180,21 @@ static unsigned long __init arch_reserved_kernel_pages(void)
#endif
/*
+ * Adaptive scale is meant to reduce sizes of hash tables on large memory
+ * machines. As memory size is increased the scale is also increased but at
+ * slower pace. Starting from ADAPT_SCALE_BASE (64G), every time memory
+ * quadruples the scale is increased by one, which means the size of hash table
+ * only doubles, instead of quadrupling as well.
+ * Because 32-bit systems cannot have large physical memory, where this scaling
+ * makes sense, it is disabled on such platforms.
+ */
+#if __BITS_PER_LONG > 32
+#define ADAPT_SCALE_BASE (64ul << 30)
+#define ADAPT_SCALE_SHIFT 2
+#define ADAPT_SCALE_NPAGES (ADAPT_SCALE_BASE >> PAGE_SHIFT)
+#endif
+
+/*
* allocate a large system hash table from bootmem
* - it is assumed that the hash table must contain an exact power-of-2
* quantity of entries
@@ -7210,6 +7225,16 @@ void *__init alloc_large_system_hash(const char *tablename,
if (PAGE_SHIFT < 20)
numentries = round_up(numentries, (1<<20)/PAGE_SIZE);
+#if __BITS_PER_LONG > 32
+ if (!high_limit) {
+ unsigned long adapt;
+
+ for (adapt = ADAPT_SCALE_NPAGES; adapt < numentries;
+ adapt <<= ADAPT_SCALE_SHIFT)
+ scale++;
+ }
+#endif
+
/* limit to 1 bucket per 2^scale bytes of low memory */
if (scale > PAGE_SHIFT)
numentries >>= (scale - PAGE_SHIFT);